Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6935. Min Act: -0.0000

Data Index: 227309 (The Pile)

Max Activating Token Index: 594

Text #1

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.7396. Min Act: -0.0000

Data Index: 298116 (The Pile)

Max Activating Token Index: 550

Text #2

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1403811 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6236. Min Act: -0.0000

Data Index: 947807 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1847443 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1189600 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6531. Min Act: -0.0000

Data Index: 730671 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6594. Min Act: -0.0000

Data Index: 756716 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6469. Min Act: -0.0000

Data Index: 659796 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5616. Min Act: -0.0000

Data Index: 225960 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1713327 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6290. Min Act: -0.0000

Data Index: 856273 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5676. Min Act: -0.0000

Data Index: 350997 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1815664 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1116658 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1657507 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6847. Min Act: -0.0000

Data Index: 832689 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1788545 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1535776 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5622. Min Act: -0.0000

Data Index: 533540 (The Pile)

Max Activating Token Index: 33